© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52725
    Prev
    Next
    INDEX
    Explanations

    strings, church, HTML, components, disorders, seat

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ERIC
    -0.12
    人士
    -0.09
    ä¸Ģæīĭ
    -0.09
    èݺ
    -0.08
    åı³æīĭ
    -0.08
    åĩºçİ°
    -0.08
    .XR
    -0.08
    edImage
    -0.08
    ages
    -0.08
    als
    -0.08
    POSITIVE LOGITS
    åĪ«çļĦ
    0.10
    åı¦å¤ĸ
    0.09
    æ¾į
    0.09
    sson
    0.08
    åĪ¥ãģ®
    0.08
    SX
    0.08
    æľ¬èº«çļĦ
    0.08
    åħ¶ä»ĸçļĦ
    0.08
    å¼ĭ
    0.08
     sobie
    0.08
    Activations Density 1.028%

    No Known Activations